[NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf (#9556)

2025-08-29 17:17:03 -07:00
parent ff9b561817
commit 5c34b4f1c7
7 changed files with 297 additions and 61 deletions
--- a/sgl-kernel/include/sgl_kernel_ops.h
+++ b/sgl-kernel/include/sgl_kernel_ops.h
@@ -394,9 +394,8 @@ void silu_and_mul_scaled_fp4_experts_quant(
    torch::Tensor& output_scale,
    torch::Tensor const& input,
    torch::Tensor const& input_global_scale,
-    torch::Tensor const& input_offset_by_experts,
-    torch::Tensor const& output_scale_offset_by_experts,
-    torch::Tensor const& mask);
+    torch::Tensor const& mask,
+    bool use_silu_and_mul);
 /*
 * From csrc/moe/cutlass_moe/w4a8
 */